def __init__(self, pth, fle):
cells = []
data_matrix = []
with open(path.join(pth, fle)) as src:
rdr = reader(src, dialect='excel-tab')
rdr.next()
rdr.next()
drugs = rdr.next()[1:]
for row in rdr:
cells.append(row[0])
data_matrix.append(np.genfromtxt(np.array(row[1:])).astype(np.float64))
cell_idx = supporting_functions.index(cells)
drug_idx = supporting_functions.index(drugs)
cell_idx_rv = dict([(value, key) for key, value in cell_idx.iteritems()])
drug_idx_rv = dict([(value, key) for key, value in drug_idx.iteritems()])
self.cell_line_2_idx = cell_idx
self.drug_2_idx = drug_idx
self.idx_2_cell_line = cell_idx_rv
self.idx_2_drug = drug_idx_rv
self.gi_50 = np.array(data_matrix)
def __init__(self, pth, fle):
cells = []
markers = []
with open(path.join(pth, fle)) as src:
rdr = reader(src, dialect='excel-tab')
rdr.next()
rdr.next()
header = rdr.next()[1:]
for row in rdr:
cells.append(row[0])
markers.append(row[1:])
cell_idx = supporting_functions.index(cells)
cell_idx_rv = dict([(value, key) for key, value in cell_idx.iteritems()])
self.cassificant_index = cell_idx
self.header = header
self.classificant_index_rv = cell_idx_rv
self.markers = markers
def __init__(self, pth, fle, alpha_bound_percentile=5):
cells = []
drugs = []
drug_versions = defaultdict(list)
plates = []
with open(path.join(pth, fle)) as src:
rdr = reader(src, dialect='excel-tab')
header = rdr.next()
for row in rdr:
expanded_drug_name = (row[1], float(row[47]))
cells.append(row[0])
drug_versions[row[1]].append(expanded_drug_name)
drugs.append(expanded_drug_name)
plates.append(row[2])
cell_idx = supporting_functions.index(set(cells))
drug_idx = supporting_functions.index(set(drugs))
plates_idx = supporting_functions.index(set(plates))
drug_versions = dict([(key, list(set(values)))
for key, values in drug_versions.iteritems()])
cell_idx_rv = dict([(value, key) for key, value in cell_idx.iteritems()])
drug_idx_rv = dict([(value, key) for key, value in drug_idx.iteritems()])
plates_idx_rv = dict([(value, key) for key, value in plates_idx.iteritems()])
cells_no = len(cell_idx)
drugs_no = len(drug_idx)
plates_no = len(plates_idx)
depth_limiter = 7
storage = np.empty((cells_no, drugs_no, depth_limiter, 10, 3))
storage.fill(np.NaN)
background = np.empty((cells_no, drugs_no, depth_limiter, 4))
background.fill(np.NaN)
t0_median = np.empty((cells_no, drugs_no, depth_limiter))
t0_median.fill(np.NaN)
t0_background = np.empty((cells_no, drugs_no, depth_limiter))
t0_background.fill(np.NaN)
tf_background = np.empty((cells_no, drugs_no, depth_limiter))
tf_background.fill(np.NaN)
background_noise = np.empty((plates_no, 2))
background_noise.fill(np.NaN)
cl_drug_replicates = np.zeros((cells_no, drugs_no))
with open(path.join(pth, fle)) as src:
rdr = reader(src, dialect='excel-tab')
test_array = rdr.next()
supporting_functions.broadcast(test_array[6:36])
for row in rdr:
cell_no = cell_idx[row[0]]
drug_no = drug_idx[(row[1], float(row[47]))]
plate_no = plates_idx[row[2]]
depth_index = min(cl_drug_replicates[cell_no, drug_no], depth_limiter-1)
storage[cell_no, drug_no, depth_index, :, :] = supporting_functions.broadcast(row[6:36])
background[cell_no, drug_no, depth_index, :] = supporting_functions.lgi(row, [4, 5, 36, 37])
t0_median[cell_no, drug_no, depth_index] = row[38]
t0_background[cell_no, drug_no, depth_index] = np.mean(
supporting_functions.lgi(row, [4, 5]).astype(np.float64)).tolist()
tf_background[cell_no, drug_no, depth_index] = np.mean(
supporting_functions.lgi(row, [36, 37]).astype(np.float64)).tolist()
background_noise[plate_no, :] = np.abs(
supporting_functions.lgi(row, [4, 36]).astype(np.float64) -
supporting_functions.lgi(row, [5, 37]).astype(
np.float64))
cl_drug_replicates[cell_no, drug_no] += 1
cl_drug_replicates[cl_drug_replicates < 1] = np.nan
alpha_bound = np.percentile(rm_nans(background_noise), 100 - alpha_bound_percentile)
std_of_tools = np.percentile(rm_nans(background_noise), 66)
background = supporting_functions.p_stabilize(background, 0.5)
t0_background = supporting_functions.p_stabilize(t0_background, 0.5)
tf_background = supporting_functions.p_stabilize(tf_background, 0.5)
storage_dblanc = storage - tf_background[:, :, :, np.newaxis, np.newaxis]
self.header_line = header
self.cell_line_2_idx = cell_idx
self.drug_2_idx = drug_idx
self.idx_2_cell_line = cell_idx_rv
self.idx_2_drug = drug_idx_rv
self.raw_data = storage_dblanc # cell_line, drug, concentration -> 3 replicates
self.background = background # cell_line, drug -> (T0_1, T0_2, T_final, T_final) backgrounds
self.t0_background = t0_background
self.t_f_background = tf_background
self.t0_median = t0_median # for each cell_line and drug contains T0
self.alpha_bound = alpha_bound # lower significance bound
self.std_of_tools = std_of_tools
self.background_noise = background_noise
self.drug_versions = dict(drug_versions) # drug names + concentrations versions
self.cl_drug_replicates = cl_drug_replicates